# This Time with Feeling: Learning Expressive Musical Performance

Source: [This Time with Feeling: Learning Expressive Musical Performance](<https://www.sota2.com/research/paper/68fa64be1e209131cea0637b>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T21:10:58.701Z

Authors: Sageev Oore, Ian Simon, Sander Dieleman, Douglas Eck, Karen Simonyan

Published: 2018-08-10T21:53:51.000Z

## Abstract

Music generation has generally been focused on either creating scores or interpreting them. We discuss differences between these two problems and propose that, in fact, it may be valuable to work in the space of direct $\\it performance$ generation: jointly predicting the notes $\\it and$ $\\it also$ their expressive timing and dynamics. We consider the significance and qualities of the data set needed for this. Having identified both a problem domain and characteristics of an appropriate data set, we show an LSTM-based recurrent network model that subjectively performs quite well on this task. Critically, we provide generated examples. We also include feedback from professional composers and musicians about some of these examples.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Music Modeling on Piano-e-Competition (val)](<https://www.sota2.com/research/sota/music-modeling-on-piano-e-competition-val.md>): Music Modeling; Piano-e-Competition (val); Val NLL: 1.969.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/1808.03715>)

[PDF](<https://arxiv.org/pdf/1808.03715.pdf>)